Trust Assessment
github-repo-mirror received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized User Input in Shell Commands, Direct Embedding of API Token in Git URL Poses Credential Exposure Risk.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Unsanitized User Input in Shell Commands The skill provides numerous `bash` commands that are intended to be executed. If an LLM or automated system substitutes user-provided input (e.g., repository names, account names, descriptions) directly into these commands without proper sanitization (e.g., shell escaping), it could lead to command injection. An attacker could craft malicious input to execute arbitrary commands on the host system. For example, the `gh repo create` command takes a `repo-name` and `description` which, if user-controlled and unsanitized, could be exploited. Implement robust input validation and shell escaping for all user-provided variables before constructing and executing shell commands. Use parameterized commands or libraries that handle escaping automatically where possible. Avoid direct string concatenation for command construction. | LLM | SKILL.md:41 | |
| HIGH | Direct Embedding of API Token in Git URL Poses Credential Exposure Risk The skill explicitly demonstrates embedding a GitHub Personal Access Token (PAT) directly within a `git push` URL (`https://TOKEN@github.com/...`). If an LLM or automated system were to execute or log this command with a real token, the token could be exposed in logs, shell history, or other insecure channels. This pattern is highly discouraged for sensitive credentials. Advise users to use environment variables (e.g., `GIT_ASKPASS` or `GITHUB_TOKEN`) or Git credential helpers instead of embedding tokens directly in URLs. If an LLM is executing, ensure tokens are passed securely (e.g., via environment variables to subprocesses) and never logged or displayed. | LLM | SKILL.md:95 |
Scan History
Embed Code
[](https://skillshield.io/report/e532c65624c1dcc3)
Powered by SkillShield